Disclosed aspects manage a shared pool of configurable computing resources. A triggering event is detected. The triggering event may be related to a resource utilization on a host of the shared pool of configurable computing resources. Based on a set of profile data, it is determined to perform an event response. The event response includes initiating a resource action or initiating an asset action. The resource action may include distributing a set of dynamically-assigned resources. The asset action corresponds to a set of assets (e.g., migrating a set of virtual machines). To change the resource utilization on the host, the event response is performed.
Legal claims defining the scope of protection. Each claim is shown in both the original legal language and a plain English translation.
1. A system for managing a shared pool of configurable computing resources, the system comprising: a memory having a set of computer readable computer instructions, and a processor for executing the set of computer readable instructions, the set of computer readable instructions including: detecting a triggering event related to a resource utilization on a host of the shared pool of configurable computing resources; determining, based on a set of profile data, to perform an event response which is selected from a group consisting of at least one of: selecting, with respect to a temporal period during which to perform the event response, a resource action in response to the set of profile data indicating to avoid a first virtual machine migration during the temporal period, selecting, with respect to the temporal period during which to perform the event response, an asset action in response to the set of profile data indicating to avoid use of a set of dynamically-assigned resources during the temporal period, selecting, with respect to a workload of a virtual machine on the host, the asset action in response to both: the set of profile data indicating to avoid a second virtual machine migration of the virtual machine from the host, and a determination that the resource action is impractical based on a group of factors, selecting, with respect to both the set of dynamically-assigned resources and a donor host, the resource action in response to the set of profile data indicating an assigned resource value exceeds a target resource value for the donor host, and selecting, with respect to the resource action and the asset action, the resource action in response to the set of profile data indicating an expected burden of executing the asset action exceeds an expected burden of executing the resource action; and performing the event response to change the resource utilization on the host.
A system manages a shared pool of computing resources. It detects when a host in the pool has high resource usage (a triggering event). Based on pre-defined profiles, it decides how to respond. This response is either a resource action (allocating dynamic resources) or an asset action (moving virtual machines). The profile data guides the selection to avoid virtual machine migrations during certain times, or to avoid using dynamic resources during other times. If migrating a VM is impractical, an asset action is selected. Also, the resource action is selected if the dynamic resource value for a donor host exceeds a target. The system also selects the resource action if it's less burdensome than migrating VMs. Finally, the chosen action is performed to reduce the high resource usage on the host.
2. The system of claim 1 , wherein: the triggering event includes the resource utilization exceeding a threshold resource utilization; the host includes a set of assets; the set of assets include a set of virtual machines; an x86 processor is absent with respect to the set of dynamically-assigned resources; and detecting, determining, and performing each occur in an automated fashion without user intervention.
The resource management system detects a triggering event when resource usage exceeds a threshold. The managed host contains virtual machines. The dynamically assigned resources don't use x86 processors. The entire process of detecting the event, determining the appropriate response, and executing the response is fully automated, without any manual user intervention. This builds upon the base system that selects between resource actions (allocating dynamic resources) or asset actions (migrating VMs) to alleviate resource constraints on a host within a shared pool of configurable computing resources based on profile data.
3. The system of claim 1 , wherein the event response includes distributing the set of dynamically-assigned resources to the host.
The resource management system, which detects high resource usage on a host and responds by either allocating dynamic resources or migrating virtual machines, performs its event response by distributing dynamically-assigned resources to the host experiencing the high usage. This action aims to alleviate the resource pressure directly by increasing available resources rather than migrating workloads. The decision between this approach and virtual machine migration is made based on profile data, as described in the base system.
4. The system of claim 1 , wherein the event response includes migrating a set of virtual machines from the host to a new host.
The resource management system, which detects high resource usage on a host and responds by either allocating dynamic resources or migrating virtual machines, performs its event response by migrating a set of virtual machines from the overloaded host to a new, less-loaded host. This offloads the resource demand from the original host, thus changing its resource utilization. The decision between this approach and dynamic resource allocation is made based on profile data, as described in the base system.
5. The system of claim 1 , wherein determining, based on the set of profile data, to perform the event response includes: computing whether to initiate the resource action or whether to initiate the asset action.
In the resource management system, the step of determining how to respond to high resource usage involves calculating whether to initiate the resource action (allocating dynamic resources) or the asset action (migrating virtual machines). This computation uses the pre-defined profile data to weigh the pros and cons of each action based on various factors, and decides which action is most appropriate given the current state of the system and the constraints defined in the profile.
6. The system of claim 1 , wherein the set of profile data includes a selection from a group consisting of at least one of: a temporal factor; a physical location factor; an unassigned resource availability factor; an assigned resource availability factor; a weighted resource availability factor; an asset priority factor; an expected performance factor; a historical usage factor; and a user-provided factor.
The profile data used by the resource management system to decide on a resource action (dynamic allocation) or asset action (VM migration) includes one or more of the following factors: the time of day, the physical location of the host, the availability of unassigned resources, the availability of assigned resources, a weighted resource availability, the priority of the virtual machines, the expected performance impact of each action, historical resource usage patterns, and user-provided preferences or rules.
7. The system of claim 1 , wherein the set of profile data includes both: a set of user input data, and a set of computing environment data.
The profile data, which guides the resource management system in choosing between dynamic resource allocation or virtual machine migration, contains both user-provided input and data automatically collected from the computing environment. This combines explicit rules and preferences set by administrators with real-time information about resource usage, performance, and system state, creating a more informed decision-making process.
8. The system of claim 1 , wherein determining, based on the set of profile data, to perform the event response includes: selecting the resource action in response to the set of profile data indicating a first parameter value for a parameter, and selecting the asset action in response to the set of profile data indicating a second parameter value for the parameter.
The resource management system selects between dynamic resource allocation and virtual machine migration based on profile data that includes parameters. If a parameter has a first value, the system chooses the resource action. If the same parameter has a second value, the system chooses the asset action. For example, if network latency (the parameter) is low (first value), allocate resources. If network latency is high (second value), migrate VMs.
9. The system of claim 1 , wherein determining, based on the set of profile data, to perform the event response includes: selecting, with respect to the host, the resource action in response to the set of profile data indicating to avoid a third virtual machine migration from the host.
The resource management system chooses between allocating dynamic resources and migrating VMs as a response to high resource usage. Specifically, the system selects the resource action if the profile data indicates that a virtual machine migration from the overloaded host should be avoided. This prioritization could be due to application requirements, service level agreements, or other operational constraints.
10. The system of claim 1 , wherein determining, based on the set of profile data, to perform the event response includes: selecting, with respect to a virtual machine on the host, the resource action in response to the set of profile data indicating to avoid a fourth virtual machine migration of the virtual machine from the host.
The resource management system chooses between allocating dynamic resources and migrating VMs. The system selects the resource action if the profile data indicates that a specific virtual machine on the overloaded host should not be migrated. This could be due to the VM's dependencies, its role in a critical service, or other reasons that make migration undesirable for that particular VM.
11. The system of claim 1 , wherein determining, based on the set of profile data, to perform the event response includes: selecting, with respect to the set of dynamically-assigned resources, the resource action in response to the set of profile data indicating an unassigned resource value exceeds a threshold unassigned resource value.
In the resource management system, the selection between dynamic resource allocation and virtual machine migration hinges on profile data. The resource action (dynamic resource allocation) is selected if the profile data shows that the amount of currently unassigned resources exceeds a defined threshold. This indicates that there are ample resources available to allocate without disrupting other workloads.
12. The system of claim 1 , further comprising: metering use of the event response; and generating an invoice based on the metered use.
The resource management system, which dynamically manages resources in response to triggering events, also tracks the usage of the event response mechanism itself. The system meters how often and to what extent the resource actions and asset actions are used. Based on this metered usage, the system generates invoices, allowing for chargeback or billing based on actual resource management activity.
13. A computer program product for managing a shared pool of configurable computing resources, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, wherein the computer readable storage medium is not a transitory signal per se, the program instructions executable by a processor to cause the processor to perform a method comprising: detecting a triggering event related to a resource utilization on a host of the shared pool of configurable computing resources; determining, based on a set of profile data, to perform an event response which is selected from a group consisting of at least one of: selecting, with respect to a temporal period during which to perform the event response, a resource action in response to the set of profile data indicating to avoid a first virtual machine migration during the temporal period, selecting, with respect to the temporal period during which to perform the event response, an asset action in response to the set of profile data indicating to avoid use of a set of dynamically-assigned resources during the temporal period, selecting, with respect to a workload of a virtual machine on the host, the asset action in response to both: the set of profile data indicating to avoid a second virtual machine migration of the virtual machine from the host, and a determination that the resource action is impractical based on a group of factors, selecting, with respect to both the set of dynamically-assigned resources and a donor host, the resource action in response to the set of profile data indicating an assigned resource value exceeds a target resource value for the donor host, and selecting, with respect to the resource action and the asset action, the resource action in response to the set of profile data indicating an expected burden of executing the asset action exceeds an expected burden of executing the resource action; and performing the event response to change the resource utilization on the host.
A computer program, stored on a non-transitory medium, manages a shared pool of computing resources. The program detects when a host in the pool has high resource usage (a triggering event). Based on pre-defined profiles, it decides how to respond. This response is either a resource action (allocating dynamic resources) or an asset action (moving virtual machines). The profile data guides the selection to avoid virtual machine migrations during certain times, or to avoid using dynamic resources during other times. If migrating a VM is impractical, an asset action is selected. Also, the resource action is selected if the dynamic resource value for a donor host exceeds a target. The system also selects the resource action if it's less burdensome than migrating VMs. Finally, the chosen action is performed to reduce the high resource usage on the host.
14. The computer program product of claim 13 , wherein at least one of: the program instructions are stored in the computer readable storage medium in a data processing system, and wherein the program instructions were downloaded over a network from a remote data processing system; or the program instructions are stored in the computer readable storage medium in a server data processing system, and wherein the program instructions are downloaded over a network to the remote data processing system for use in a second computer readable storage medium with the remote data processing system.
The computer program product for managing computing resources (as described in claim 13) can be stored and run within a data processing system. The program can be installed by downloading it from a remote server over a network. Alternatively, the program can be stored on a server and then downloaded to a remote system for execution. This describes different methods for distributing and installing the resource management software.
15. A system for managing a shared pool of configurable computing resources, the system comprising: a memory having a set of computer readable computer instructions, and a processor for executing the set of computer readable instructions, the set of computer readable instructions including: detecting a triggering event related to a resource utilization on a host of the shared pool of configurable computing resources; determining, based on a set of profile data, to perform an event response which includes: selecting, with respect to a resource action and an asset action, the asset action in response to the set of profile data indicating an expected burden of executing the resource action exceeds an expected burden of executing the asset action; and performing the event response to change the resource utilization on the host.
A system manages a shared pool of computing resources. It detects when a host in the pool has high resource usage (a triggering event). Based on pre-defined profiles, it decides how to respond. It selects the asset action (moving virtual machines) if the expected burden of executing the resource action (allocating dynamic resources) exceeds the expected burden of executing the asset action. Finally, the chosen action is performed to reduce the high resource utilization on the host.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
January 3, 2016
April 11, 2017
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.